Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Explainable AI-Enhanced Deep Learning for Pumpkin Leaf Disease Detection: A Comparative Analysis of CNN Architectures

Md. Arafat Alam Khandaker, Ziyan Shirin Raha, Shifat Islam, Tashreef Muhammad

TL;DR

The paper addresses automated, explainable detection of pumpkin leaf diseases using multiple CNN architectures. It evaluates seven pretrained CNNs on a 2,000-image, five-class dataset and augments predictions with XAI techniques (Grad-CAM, Grad-CAM++, Score-CAM, Layer-CAM) to reveal decision regions. ResNet50 emerges as the top performer with an accuracy of $0.905$, while XAI analyses provide interpretable heatmaps to enhance trust. The work demonstrates a practical, interpretable pipeline for plant-disease diagnostics with potential impact on precision agriculture and timely disease management.

Abstract

Pumpkin leaf diseases are significant threats to agricultural productivity, requiring a timely and precise diagnosis for effective management. Traditional identification methods are laborious and susceptible to human error, emphasizing the necessity for automated solutions. This study employs on the "Pumpkin Leaf Disease Dataset", that comprises of 2000 high-resolution images separated into five categories. Downy mildew, powdery mildew, mosaic disease, bacterial leaf spot, and healthy leaves. The dataset was rigorously assembled from several agricultural fields to ensure a strong representation for model training. We explored many proficient deep learning architectures, including DenseNet201, DenseNet121, DenseNet169, Xception, ResNet50, ResNet101 and InceptionResNetV2, and observed that ResNet50 performed most effectively, with an accuracy of 90.5% and comparable precision, recall, and F1-Score. We used Explainable AI (XAI) approaches like Grad-CAM, Grad-CAM++, Score-CAM, and Layer-CAM to provide meaningful representations of model decision-making processes, which improved understanding and trust in automated disease diagnostics. These findings demonstrate ResNet50's potential to revolutionize pumpkin leaf disease detection, allowing for earlier and more accurate treatments.

Explainable AI-Enhanced Deep Learning for Pumpkin Leaf Disease Detection: A Comparative Analysis of CNN Architectures

TL;DR

The paper addresses automated, explainable detection of pumpkin leaf diseases using multiple CNN architectures. It evaluates seven pretrained CNNs on a 2,000-image, five-class dataset and augments predictions with XAI techniques (Grad-CAM, Grad-CAM++, Score-CAM, Layer-CAM) to reveal decision regions. ResNet50 emerges as the top performer with an accuracy of , while XAI analyses provide interpretable heatmaps to enhance trust. The work demonstrates a practical, interpretable pipeline for plant-disease diagnostics with potential impact on precision agriculture and timely disease management.

Abstract

Pumpkin leaf diseases are significant threats to agricultural productivity, requiring a timely and precise diagnosis for effective management. Traditional identification methods are laborious and susceptible to human error, emphasizing the necessity for automated solutions. This study employs on the "Pumpkin Leaf Disease Dataset", that comprises of 2000 high-resolution images separated into five categories. Downy mildew, powdery mildew, mosaic disease, bacterial leaf spot, and healthy leaves. The dataset was rigorously assembled from several agricultural fields to ensure a strong representation for model training. We explored many proficient deep learning architectures, including DenseNet201, DenseNet121, DenseNet169, Xception, ResNet50, ResNet101 and InceptionResNetV2, and observed that ResNet50 performed most effectively, with an accuracy of 90.5% and comparable precision, recall, and F1-Score. We used Explainable AI (XAI) approaches like Grad-CAM, Grad-CAM++, Score-CAM, and Layer-CAM to provide meaningful representations of model decision-making processes, which improved understanding and trust in automated disease diagnostics. These findings demonstrate ResNet50's potential to revolutionize pumpkin leaf disease detection, allowing for earlier and more accurate treatments.
Paper Structure (11 sections, 4 figures, 2 tables)

This paper contains 11 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Methodology
  4. Dataset
  5. Proposed Methodology
  6. Result Analysis
  7. Experimental setup
  8. Evaluation
  9. Model Interpretation using XAI
  10. Limitations & Future Work
  11. Conclusion

Figures (4)

  • Figure 1: Displays Representation Samples from the Dataset Showcasing Various Categories of Pumpkin Leaves
  • Figure 2: Implied Methodology for Classifying Pumpkin Leaf Using Explainable AI Techniques
  • Figure 3: Confusion Matrix of Pre-Trained CNNs for Pumpkin Leaf Classification
  • Figure 4: AI insights, Including GradCAM, GradCAM++, ScoreCAM, and LayerCAM, Provides Distinct Perspectives on the Source Image for Pumpkin Leaf Classification.